Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 237 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0508. Min Range: -6.0508
Max Act: 6.0508. Min Act: -0.1700
Data Index: 1418667 (Python Code)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.8633. Min Act: -0.1700
Data Index: 1648050 (Python Code)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.7071. Min Act: -0.1700
Data Index: 1374369 (Python Code)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5821. Min Act: -0.1700
Data Index: 1420737 (Python Code)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5821. Min Act: -0.1700
Data Index: 1633410 (Python Code)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5821. Min Act: -0.1700
Data Index: 1562117 (Python Code)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5821. Min Act: -0.1700
Data Index: 1464675 (Python Code)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5821. Min Act: -0.1700
Data Index: 1554865 (Python Code)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5821. Min Act: -0.1700
Data Index: 1577360 (Python Code)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.6133. Min Act: -0.1700
Data Index: 1450715 (Python Code)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.4883. Min Act: -0.1700
Data Index: 1465539 (Python Code)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5508. Min Act: -0.1700
Data Index: 1400016 (Python Code)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5196. Min Act: -0.1700
Data Index: 1517925 (Python Code)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5508. Min Act: -0.1700
Data Index: 1622700 (Python Code)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5508. Min Act: -0.1700
Data Index: 1504030 (Python Code)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.4571. Min Act: -0.1700
Data Index: 1581380 (Python Code)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.4883. Min Act: -0.1700
Data Index: 1459361 (Python Code)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.4883. Min Act: -0.1700
Data Index: 1428849 (Python Code)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.5196. Min Act: -0.1700
Data Index: 1613100 (Python Code)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0508. Min Range: -6.0508
Max Act: 5.4883. Min Act: -0.1700
Data Index: 1521181 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19